新的LLM解码框架保证语法上有效的结构化输出

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-31 04:00

研究人员开发了一种新的大型语言模型解码框架，以确保语法上有效的结构化输出，例如JSON、SQL和线性时序逻辑。该框架基于下推自动机，使用前瞻引导和可达性标签来修剪搜索范围并提高完成质量。实验表明，与现有方法相比，它具有持续的语法有效性和增强的性能。 AI

影响增强了LLM生成结构化数据的可靠性，这对于代码和数据处理应用至关重要。

排序理由该集群包含一篇详细介绍LLM解码新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM解码新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Vincenzo Collura, Karim Tit, Eleonora Giunchiglia, Mike Papadakis, Maxime Cordy · 2026-08-31 04:00

保持界限：距离引导解码以保证无上下文语法合规性

arXiv:2608.28229v1 Announce Type: cross Abstract: Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free grammars, many practical decoders enforce local prefix feasibility: each token …